audit_log

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses the fields it records (model, cost, confidence, reasoning chain, human approval status), which is informative. However, it does not mention any side effects (e.g., permanence of the log, auth/permission requirements, rate limits) or whether the operation is synchronous. For a logging tool, this is a moderate level of transparency, but gaps remain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the core action ('Log an AI marketing action') and then lists the recorded fields. There is no redundant or filler text; every clause adds value. It is concise and well-structured for quick parsing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite its concise phrasing, the description is not complete given the tool's complexity (11 parameters, nested objects, no output schema). It does not explain return values, the significance of many parameters, or the expected behavior when fields are omitted (e.g., defaults). The absence of annotations amplifies the need for more context, which is not provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter meanings. It clarifies the purpose of model, cost, confidence, reasoning_chain, and human_approved. However, it leaves action, brand_id, metadata, input_tokens, output_tokens, and result_summary unexplained. With 11 parameters, covering only 5 is insufficient; an agent would not know the significance of the omitted ones without further context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb and resource: 'Log an AI marketing action with full audit trail.' It also enumerates the key data recorded (model, cost, confidence, reasoning chain, human approval status), which makes its function unambiguous. The verb 'log' distinguishes it from retrieval siblings like audit_get_log and audit_get_cost_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context (when an AI marketing action needs to be recorded) but does not explicitly state when to use this tool versus alternatives. It does not mention audit_get_log or audit_get_cost_summary as alternatives, nor does it specify conditions for choosing this tool over others. The verb 'log' gives a hint, but explicit guidance is absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.